Please use this identifier to cite or link to this item:
|Title:||Deep learning for communication signal classification - part B||Authors:||Chua, Randal Wei Bin||Keywords:||Engineering::Electrical and electronic engineering::Wireless communication systems||Issue Date:||2022||Publisher:||Nanyang Technological University||Source:||Chua, R. W. B. (2022). Deep learning for communication signal classification - part B. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157947||Project:||A3071-211||Abstract:||In recent years, Deep Learning methods have achieved great success in many applications due to their powerful feature extraction capabilities and end-to-end training mechanism. Recently, communication signal modulation classification has been introduced. By using automatic classifiers, it will help to determine the types of modulated signals present in the environment. This has important applications in defence and commercial areas. In this project, the performance of Convolutional Neural Networks (CNN) and Long ShortTerm Memory (LSTM) for some of the common communication signals classification will be investigated. These signals include Gaussian Frequency Shift Keying, Binary Phase Shift Keying, Broadcast Frequency Modulation, Double Sideband Amplitude Modulation and Single Sideband Amplitude Modulation. In the first part of this project, much literature was read about neural networks, deep learning as well as their different models. The next part of the project focuses on MATLAB and what has been done within its workspace such as the generation of the data set. Lastly, the base different models were built, trained, and tested. Different experiments were tested on the models by altering either the parameters of the model or the dataset that is fed into them. By conducting these tests, we can find relationships between these models and present some conclusions. By comparing the results with each other, the conclusion is that in general, the CNN model has better performance||URI:||https://hdl.handle.net/10356/157947||Schools:||School of Electrical and Electronic Engineering||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Student Reports (FYP/IA/PA/PI)|
Updated on Dec 2, 2023
Updated on Dec 2, 2023
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.